Yes, you can move your ChatGPT or Claude conversation history to Safeguard. Request a data export from ChatGPT or Claude, then upload the zip in Safeguard under Settings, Import from another AI, or paste the download link from the export email and let Safeguard fetch it. Gemini history comes across as a Google Takeout file you upload.
You never give Safeguard another service's password: you export your own data, then bring the file or link. This guide covers conversations.
Key takeaways
- ChatGPT and Claude: export from the product's settings, then upload the zip or paste the export link.
- Gemini: no official Google API covers Gemini chat history today, so use Google Takeout (My Activity, Gemini Apps, JSON) and upload.
- No passwords: Safeguard works only from an export you request yourself.
- Where it lands: imported chats appear in Recents with an Imported from tag, and are searchable.
Can I import my ChatGPT history into Safeguard?
Yes. Per OpenAI's help article, sign in to ChatGPT on the web, open your profile menu, then Settings, then Data controls, and under Export data select Export, then Confirm export. ChatGPT emails or texts you when the export is ready, which OpenAI says can take up to 7 days. The link expires 24 hours after you receive it, and OpenAI says to download while signed in to the same account.
Self-service export is not offered in Business, Enterprise or ChatGPT for Healthcare workspaces; ask the workspace owner there.
In Safeguard, open Settings, choose Import from another AI, pick ChatGPT / OpenAI and drop the zip on the page as it is.
Can I import my Claude conversations into Safeguard?
Yes. Anthropic's help article says individual users on Free, Pro, Max and Ultra plans export from Settings, then Privacy, then Export data, on the web app or Claude Desktop (not the mobile apps). A download link arrives by email.
Note three details. You must be signed in to download with the link. The link expires after 24 hours and may work only once. The export holds conversation and account data, but not the original files you uploaded. On Team and Enterprise plans, an owner must turn on member exports first.
In Safeguard, pick Claude.ai as the source and upload the zip as it is.
How does "Paste your export link" work?
To skip downloading and re-uploading a large file, use Paste your export link on the Import page. Request the export with the page's buttons, then paste the download link from the email. Safeguard fetches the zip and imports it.
Treat the link like a password, because anyone with it can download your history. Safeguard uses it once, does not store it, and fetches only from ChatGPT's and Claude's own download hosts.
One caveat: OpenAI and Anthropic both say to open their links while signed in. If a link needs your sign-in, the import stops and asks you to upload the zip instead, and a single-use Claude link may then need a fresh export. The surest path is to download the zip and upload it.
Can I import my Gemini chats?
Yes, with a file. Google's Data Portability API has no Gemini scope today. In Google Takeout, pick My Activity, narrow it to Gemini Apps, set the format to JSON and export. Upload that zip with Gemini as the source. Choose JSON: the importer does not read an HTML export.
ChatGPT, Claude and Gemini import compared
| Source | How you import | What comes across | Caveats |
|---|---|---|---|
| ChatGPT | Settings, Data controls, Export; upload the zip or paste the link | Your conversations | Up to 7 days to arrive; link expires in 24 hours; no self-service export in Business or Enterprise |
| Claude | Settings, Privacy, Export data; upload the zip or paste the link | Your conversations | Link needs sign-in, expires in 24 hours, may work once; uploaded files not included |
| Gemini | Google Takeout, My Activity, Gemini Apps, JSON; upload the zip | Your Gemini Apps activity | No official API, so no link route; JSON only |
What happens to my data during the import?
Tool output is shortened to a one-line note. Very long conversations are split into linked parts. Importing the same export again never makes duplicates.
Large uploads go in pieces and resume if your connection drops.
A third route, a browser extension that reads your own signed-in ChatGPT or Claude tab after you consent, is coming. Until then, use the upload or the export link.
What can I do with my history in Safeguard?
Imported chats sit in Recents, so past threads stay in reach. You can also keep Claude: Safeguard's MCP server lets Claude call Safeguard tools, and we cover securing Claude Code MCP deployments. For how a security model differs from a general one, see choosing a specialised security LLM. Before reusing code from an old thread, read the risk of copy-pasted code from AI chats. Teams consolidating assistants can start with shadow AI discovery.
Common mistakes
- Waiting on the link. ChatGPT and Claude links expire 24 hours after the email.
- Unzipping first. Upload the zip as it is.
- Picking HTML in Takeout. Gemini imports need JSON.
- Sharing the link. Paste it only into the Import page.
Why dependency hygiene still matters after you switch
Switching assistants often means writing more code with AI help, and that code pulls in open source dependencies. These practices keep them patched, whichever assistant wrote the code.
Fix it without waiting for upstream
Whatever the vulnerability, most of the risk sits in two gaps. The first is the time between a fix being published and that fix actually running in your production builds. The second, and worse, is the time before any fix exists at all, while a maintainer works out a patch and a release schedule. Waiting through both gaps is a habit, not a requirement. Safeguard gives teams three ways to close them.
1. Autonomous remediation: pull requests, not tickets
When a fixed version exists, Griffin, Safeguard's security model, opens a policy gated pull request that moves the affected dependency to the safe version, and your own CI runs your tests on it before anyone merges. You can run it on one repository or in bulk across every project that carries the vulnerable version. Remediation categories include dependencies, licenses, security posture and findings, and each one is set separately. Reachability analysis ranks the vulnerable code paths your application actually calls first, so the first pull requests you merge are the ones that matter most. Auto-merge is a separate switch and stays off by default, so your team decides what merges on its own and what still needs a human approval.
2. Gold Open Source: the safe version in seconds, free
gold.safeguard.sh is free and needs no login. Search any CVE or package to see affected and fixed versions, CVSS, EPSS, CISA KEV status and a recommended safe version, or use the "Am I affected?" checker. The same data is available through a free read API, README status badges and RSS threat feeds.
3. Gold Registry: start from components that are already fixed
Safeguard Gold rebuilds patched versions of open-source packages and images from source, signs each build, attaches an SBOM, SLSA provenance and VEX, and serves them from registry.safeguard.sh to your organization. Every Gold artifact is held continuously to zero exploitable critical or high CVEs and a completed license check, with signed build provenance (signed with Safeguard's key and verifiable with cosign, SLSA Build Level 3 as the design target) and a public evidence page you can hand to an auditor. An artifact loses its Gold badge if it regresses. Teams can point their own package directory at the registry so hardened equivalents resolve without changing how developers install anything.
When upstream has no fix yet, or will not ship one, Safeguard first works to get the fix accepted upstream. If the issue is severe or upstream will not move, Safeguard builds a fork, fixes the vulnerability there and publishes a hardened Gold build, so you are not stuck on a maintainer's release schedule. You can also request a hardened build of a specific package. Ask which packages it covers before you plan around it.
| Your situation | What to use |
|---|---|
| A fixed version exists | Autonomous remediation opens the upgrade pull request; Gold Open Source confirms the safe version |
| You need to know today whether you are affected | Gold Open Source lookup and "Am I affected?" checker, free and without login |
| You want vulnerable versions to stop shipping | Safeguard policies and gates in CI |
| Upstream has no fix yet, or will not ship one | A custom Gold request; fork and patch |
| You want to start clean on new projects | Pull hardened components and images from Gold Registry |
One honest limit: when the vulnerable code lives in a vendor appliance, a hosted service or an operating system runtime you do not build yourself, the fix still has to come from that vendor or distribution. The steps above apply to the open source dependencies and container images you build and ship, which is where most teams carry the largest and least tracked share of their exposure.
See how Safeguard would help
If you keep Claude, this demo connects it to the Safeguard MCP server with OAuth and picks which tools it can use.
Click through it at your own pace, or open it full screen.
This real Safeguard CLI session fixes a lodash CVE, running npm install and npm test only with your approval.
Click through it at your own pace, or open it full screen. Get Safeguard at safeguard.sh/download.
FAQ
How do I transfer my Claude chats to Safeguard?
Export under Settings, Privacy, Export data on the web or desktop app, then upload the zip or paste the link.
Do I need my ChatGPT or Claude password?
No. You export from your own account and bring the file or link. Safeguard never asks for another service's password.
Can I import Gemini conversations?
Yes, through Google Takeout (My Activity, Gemini Apps, JSON). There is no official Google API for it today.
Does the import bring my uploaded files?
Not from Claude: its export leaves out the original files you uploaded. This guide covers conversations.
What if my export link expired?
Request a new export. Both links expire 24 hours after the email.
Sources
- OpenAI Help Center: Exporting your ChatGPT history and data
- Claude Help Center: Export your Claude data
- Google Account Help: How to download your Google data
- Google Data Portability API scopes
- Safeguard app, Settings, Import from another AI (page text as of 22 November 2026)
Last reviewed: 22 November 2026.